Boosting the Sliding Frank-Wolfe solver for 3D deconvolution

TL;DR

This paper enhances the Sliding Frank-Wolfe algorithm for 3D deconvolution, making it more computationally efficient while maintaining its effectiveness in gridless sparse optimization tasks.

Contribution

It introduces a boosting strategy for the Sliding Frank-Wolfe algorithm that significantly reduces computation time in 3D deconvolution applications.

Findings

Boosted SFW achieves similar results faster

Reduces computational burden in 3D deconvolution

Maintains analytical and practical properties

Abstract

In the context of gridless sparse optimization, the Sliding Frank Wolfe algorithm recently introduced has shown interesting analytical and practical properties. Nevertheless, is application to large data, such as in the case of 3D deconvolution, is computationally heavy. In this paper, we investigate a strategy for leveraging this burden, in order to make this method more tractable for 3D deconvolution. We show that a boosted SFW can achieve the same results in a significantly reduced amount of time.